© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12907
    Prev
    Next
    INDEX
    Explanations

    pertaining to memory-related terms and functions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to memory and cognitive processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wered
    -0.82
    ounty
    -0.70
     Manson
    -0.69
    abad
    -0.68
     Soda
    -0.67
    osher
    -0.67
     Git
    -0.66
     spotlight
    -0.65
     Konami
    -0.65
    ivil
    -0.64
    POSITIVE LOGITS
     impairment
    1.29
     faculties
    1.17
     impair
    1.12
     abilities
    1.11
     comprehension
    1.11
     skills
    1.09
     impaired
    1.08
     stimuli
    1.02
     disorders
    0.99
     ability
    0.99
    Activations Density 0.205%

    No Known Activations